Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to social actions and political conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Handling
    -0.16
     Selling
    -0.16
     нанеÑģ
    -0.15
     yoktur
    -0.15
     Handling
    -0.15
    æ¡ij
    -0.14
    (Encoding
    -0.14
    èm
    -0.14
     kunt
    -0.14
     Killing
    -0.13
    POSITIVE LOGITS
     being
    1.00
    being
    0.80
     Being
    0.71
    Being
    0.66
     becoming
    0.58
     sendo
    0.56
    被
    0.55
     siendo
    0.52
     essere
    0.50
    -being
    0.49
    Act Density 0.074%

    No Known Activations